On the (In)security of Peer-to-Peer Decentralized Machine Learning

Understand

In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning -- a collaborative machine learning framework aimed at addressing the main limitations of federated learning.

• We introduce a suite of novel attacks for both passive and active decentralized adversaries.
• We demonstrate that, contrary to what is claimed by decentralized learning proposers, decentralized learning does not offer any security advantage over federated learning.
• Rather, it increases the attack surface enabling any user in the system to perform privacy attacks such as gradient inversion, and even gain full control over honest users' local model.